Comment Stateward vous protège contre code généré par ia non sécurisé
La menace
Copilot, Cursor et Claude écrivent une part croissante du code de production avec moins de revue humaine par ligne — ouvrant des modes de défaillance que les scanners classiques n’ont jamais visés : défauts non sécurisés, configs trop permissives, dépendances hallucinées et surfaces d’injection de prompt.
Comment Stateward le détecte
Stateward cible spécifiquement les schémas de défaillance du code écrit par IA, avec des packs de revue adverse par langage et des vérifications spécifiques à l’IA pour les dépendances hallucinées, les défauts trop permissifs et les surfaces d’injection de prompt — la catégorie que tous les acteurs établis ont manquée.
Alertes récentes de cette classe
- criticalAI-GROK-BANKR-WALLET-2026In early May 2026 an attacker drained roughly $150,000 from an AI-powered crypto trading agent on X (Twitter) through prompt injection, an exploit of Grok and the linked Bankrbot agent documented by AI-security researchers including Giskard and NeuralTrust. The attacker posted a Morse-code-encoded message on X and asked Grok to translate it; Grok decoded the obfuscated payload, which contained hidden financial instructions, and the encoding let the untrusted post slip past content filters. Grok processed this user-supplied X content as a trusted directive with no separation between conversation input and authorized commands, then relayed the decoded instruction to the linked Bankrbot agent, which executed it as a legitimate order. Combined with a previously transferred Bankr Club Membership NFT that granted elevated 'Executive' wallet permissions, Bankrbot sent about 3 billion DRB tokens (roughly $150,000) on the Base network to the attacker's wallet, with no human-in-the-loop or circuit breaker on the high-value transfer. About 80% of the funds were later returned after the community identified the attacker.
- highAI-CLAUDECODE-SOURCEMAP-2026On March 31, 2026, Anthropic accidentally shipped the full source of its Claude Code CLI inside a published npm package. A missing .npmignore rule for *.map left a roughly 59.8 MB source map in the tarball, embedding about 512,000 lines of unobfuscated TypeScript across some 1,900 files, including internal prompts, tool definitions and architecture. The root cause was a packaging failure compounded by a bundler bug: Bun continued emitting source maps even when generation was disabled, and nothing stripped or excluded them before publish. Because npm releases are immutable and mirrored instantly, the source was cloned, dissected and re-hosted within hours, and a clean-room reimplementation reached tens of thousands of GitHub stars the same day. It is a textbook source-map disclosure: the sourcesContent field of a .map file carries the original code verbatim, so a single map left in a shipped artifact hands an attacker the entire codebase, comments and all. The same class hit Apple's App Store web front-end in November 2025, where production source maps left enabled let a researcher reconstruct and publish the full client source.
- mediumAI-SECRETS-SPRAWL-2025GitGuardian's State of Secrets Sprawl research found that AI coding assistants are driving a surge in leaked credentials on public GitHub. AI-assisted commits leaked secrets at roughly twice the baseline rate, with Claude Code-assisted commits showing a 3.2% leak rate versus 1.5% for human-only commits, contributing to 28.65 million new hardcoded secrets added to public GitHub in 2025 (a 34% year-over-year increase). The study also found 24,008 unique secrets in MCP configuration files, where setup guides often instruct developers to paste API keys directly into config.
- criticalAI-COPILOT-CAMOLEAK-2025Legit Security disclosed CamoLeak (CVSS 9.6), a critical vulnerability in GitHub Copilot Chat enabling silent exfiltration of private source code and secrets. The attack combined remote prompt injection via hidden pull-request comments with a CSP bypass that abused GitHub's own Camo image proxy: injected instructions made Copilot extract sensitive repo context, encode it character-by-character into a pre-generated dictionary of Camo image URLs, and leak it through image requests to an attacker server. GitHub mitigated it by disabling image rendering in Copilot Chat in August 2025.
Vérifiez votre dépôt
Connectez un dépôt et Stateward analyse votre prochaine pull request — en lecture seule, gratuit pour les particuliers et l’open source.
Conçu pour mériter votre confiance
Lecture seule & éphémère
Stateward commente, sans jamais pousser, fusionner ou stocker vos clés.
Hébergement souverain UE
Code et données restent hébergés en UE via Citadea — pensé pour NIS2, DORA et le CRA.
Conscient de tout le code
Raisonne sur le graphe d’appels et les frontières de confiance, pas seulement le diff.
Stateward est en bêta et recrute des partenaires de conception. Conçu par Yggdrasil Digital.